1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518
|
/*
Copyright (C) 2009,2010 Stig Brautaset. All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice, this
list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright notice,
this list of conditions and the following disclaimer in the documentation
and/or other materials provided with the distribution.
* Neither the name of the author nor the names of its contributors may be used
to endorse or promote products derived from this software without specific
prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#import "SBJsonParser.h"
@interface SBJsonParser ()
- (BOOL)scanValue:(NSObject **)o;
- (BOOL)scanRestOfArray:(NSMutableArray **)o;
- (BOOL)scanRestOfDictionary:(NSMutableDictionary **)o;
- (BOOL)scanRestOfNull:(NSNull **)o;
- (BOOL)scanRestOfFalse:(NSNumber **)o;
- (BOOL)scanRestOfTrue:(NSNumber **)o;
- (BOOL)scanRestOfString:(NSMutableString **)o;
// Cannot manage without looking at the first digit
- (BOOL)scanNumber:(NSNumber **)o;
- (BOOL)scanHexQuad:(unichar *)x;
- (BOOL)scanUnicodeChar:(unichar *)x;
- (BOOL)scanIsAtEnd;
@end
#define skipWhitespace(c) while (isspace(*c)) c++
#define skipDigits(c) while (isdigit(*c)) c++
@implementation SBJsonParser
static char ctrl[0x22];
+ (void)initialize {
ctrl[0] = '\"';
ctrl[1] = '\\';
for (int i = 1; i < 0x20; i++)
ctrl[i+1] = i;
ctrl[0x21] = 0;
}
- (id)objectWithString:(NSString *)repr {
[self clearErrorTrace];
if (!repr) {
[self addErrorWithCode:EINPUT description:@"Input was 'nil'"];
return nil;
}
depth = 0;
c = [repr UTF8String];
id o;
if (![self scanValue:&o]) {
return nil;
}
// We found some valid JSON. But did it also contain something else?
if (![self scanIsAtEnd]) {
[self addErrorWithCode:ETRAILGARBAGE description:@"Garbage after JSON"];
return nil;
}
NSAssert1(o, @"Should have a valid object from %@", repr);
// Check that the object we've found is a valid JSON container.
if (![o isKindOfClass:[NSDictionary class]] && ![o isKindOfClass:[NSArray class]]) {
[self addErrorWithCode:EFRAGMENT description:@"Valid fragment, but not JSON"];
return nil;
}
return o;
}
- (id)objectWithString:(NSString*)repr error:(NSError**)error {
id tmp = [self objectWithString:repr];
if (tmp)
return tmp;
if (error)
*error = [self.errorTrace lastObject];
return nil;
}
/*
In contrast to the public methods, it is an error to omit the error parameter here.
*/
- (BOOL)scanValue:(NSObject **)o
{
skipWhitespace(c);
switch (*c++) {
case '{':
return [self scanRestOfDictionary:(NSMutableDictionary **)o];
break;
case '[':
return [self scanRestOfArray:(NSMutableArray **)o];
break;
case '"':
return [self scanRestOfString:(NSMutableString **)o];
break;
case 'f':
return [self scanRestOfFalse:(NSNumber **)o];
break;
case 't':
return [self scanRestOfTrue:(NSNumber **)o];
break;
case 'n':
return [self scanRestOfNull:(NSNull **)o];
break;
case '-':
case '0'...'9':
c--; // cannot verify number correctly without the first character
return [self scanNumber:(NSNumber **)o];
break;
case '+':
[self addErrorWithCode:EPARSENUM description: @"Leading + disallowed in number"];
return NO;
break;
case 0x0:
[self addErrorWithCode:EEOF description:@"Unexpected end of string"];
return NO;
break;
default:
[self addErrorWithCode:EPARSE description: @"Unrecognised leading character"];
return NO;
break;
}
NSAssert(0, @"Should never get here");
return NO;
}
- (BOOL)scanRestOfTrue:(NSNumber **)o
{
if (!strncmp(c, "rue", 3)) {
c += 3;
*o = [NSNumber numberWithBool:YES];
return YES;
}
[self addErrorWithCode:EPARSE description:@"Expected 'true'"];
return NO;
}
- (BOOL)scanRestOfFalse:(NSNumber **)o
{
if (!strncmp(c, "alse", 4)) {
c += 4;
*o = [NSNumber numberWithBool:NO];
return YES;
}
[self addErrorWithCode:EPARSE description: @"Expected 'false'"];
return NO;
}
- (BOOL)scanRestOfNull:(NSNull **)o {
if (!strncmp(c, "ull", 3)) {
c += 3;
*o = [NSNull null];
return YES;
}
[self addErrorWithCode:EPARSE description: @"Expected 'null'"];
return NO;
}
- (BOOL)scanRestOfArray:(NSMutableArray **)o {
if (maxDepth && ++depth > maxDepth) {
[self addErrorWithCode:EDEPTH description: @"Nested too deep"];
return NO;
}
*o = [NSMutableArray arrayWithCapacity:8];
for (; *c ;) {
id v;
skipWhitespace(c);
if (*c == ']' && c++) {
depth--;
return YES;
}
if (![self scanValue:&v]) {
[self addErrorWithCode:EPARSE description:@"Expected value while parsing array"];
return NO;
}
[*o addObject:v];
skipWhitespace(c);
if (*c == ',' && c++) {
skipWhitespace(c);
if (*c == ']') {
[self addErrorWithCode:ETRAILCOMMA description: @"Trailing comma disallowed in array"];
return NO;
}
}
}
[self addErrorWithCode:EEOF description: @"End of input while parsing array"];
return NO;
}
- (BOOL)scanRestOfDictionary:(NSMutableDictionary **)o
{
if (maxDepth && ++depth > maxDepth) {
[self addErrorWithCode:EDEPTH description: @"Nested too deep"];
return NO;
}
*o = [NSMutableDictionary dictionaryWithCapacity:7];
for (; *c ;) {
id k, v;
skipWhitespace(c);
if (*c == '}' && c++) {
depth--;
return YES;
}
if (!(*c == '\"' && c++ && [self scanRestOfString:&k])) {
[self addErrorWithCode:EPARSE description: @"Object key string expected"];
return NO;
}
skipWhitespace(c);
if (*c != ':') {
[self addErrorWithCode:EPARSE description: @"Expected ':' separating key and value"];
return NO;
}
c++;
if (![self scanValue:&v]) {
NSString *string = [NSString stringWithFormat:@"Object value expected for key: %@", k];
[self addErrorWithCode:EPARSE description: string];
return NO;
}
[*o setObject:v forKey:k];
skipWhitespace(c);
if (*c == ',' && c++) {
skipWhitespace(c);
if (*c == '}') {
[self addErrorWithCode:ETRAILCOMMA description: @"Trailing comma disallowed in object"];
return NO;
}
}
}
[self addErrorWithCode:EEOF description: @"End of input while parsing object"];
return NO;
}
- (BOOL)scanRestOfString:(NSMutableString **)o
{
// if the string has no control characters in it, return it in one go, without any temporary allocations.
size_t len = strcspn(c, ctrl);
if (len && *(c + len) == '\"')
{
*o = [[[NSMutableString alloc] initWithBytes:(char*)c length:len encoding:NSUTF8StringEncoding] autorelease];
c += len + 1;
return YES;
}
*o = [NSMutableString stringWithCapacity:16];
do {
// First see if there's a portion we can grab in one go.
// Doing this caused a massive speedup on the long string.
len = strcspn(c, ctrl);
if (len) {
// check for
id t = [[NSString alloc] initWithBytesNoCopy:(char*)c
length:len
encoding:NSUTF8StringEncoding
freeWhenDone:NO];
if (t) {
[*o appendString:t];
[t release];
c += len;
}
}
if (*c == '"') {
c++;
return YES;
} else if (*c == '\\') {
unichar uc = *++c;
switch (uc) {
case '\\':
case '/':
case '"':
break;
case 'b': uc = '\b'; break;
case 'n': uc = '\n'; break;
case 'r': uc = '\r'; break;
case 't': uc = '\t'; break;
case 'f': uc = '\f'; break;
case 'u':
c++;
if (![self scanUnicodeChar:&uc]) {
[self addErrorWithCode:EUNICODE description: @"Broken unicode character"];
return NO;
}
c--; // hack.
break;
default:
[self addErrorWithCode:EESCAPE description: [NSString stringWithFormat:@"Illegal escape sequence '0x%x'", uc]];
return NO;
break;
}
CFStringAppendCharacters((CFMutableStringRef)*o, &uc, 1);
c++;
} else if (*c < 0x20) {
[self addErrorWithCode:ECTRL description: [NSString stringWithFormat:@"Unescaped control character '0x%x'", *c]];
return NO;
} else {
NSLog(@"should not be able to get here");
}
} while (*c);
[self addErrorWithCode:EEOF description:@"Unexpected EOF while parsing string"];
return NO;
}
- (BOOL)scanUnicodeChar:(unichar *)x
{
unichar hi, lo;
if (![self scanHexQuad:&hi]) {
[self addErrorWithCode:EUNICODE description: @"Missing hex quad"];
return NO;
}
if (hi >= 0xd800) { // high surrogate char?
if (hi < 0xdc00) { // yes - expect a low char
if (!(*c == '\\' && ++c && *c == 'u' && ++c && [self scanHexQuad:&lo])) {
[self addErrorWithCode:EUNICODE description: @"Missing low character in surrogate pair"];
return NO;
}
if (lo < 0xdc00 || lo >= 0xdfff) {
[self addErrorWithCode:EUNICODE description:@"Invalid low surrogate char"];
return NO;
}
hi = (hi - 0xd800) * 0x400 + (lo - 0xdc00) + 0x10000;
} else if (hi < 0xe000) {
[self addErrorWithCode:EUNICODE description:@"Invalid high character in surrogate pair"];
return NO;
}
}
*x = hi;
return YES;
}
- (BOOL)scanHexQuad:(unichar *)x
{
*x = 0;
for (int i = 0; i < 4; i++) {
unichar uc = *c;
c++;
int d = (uc >= '0' && uc <= '9')
? uc - '0' : (uc >= 'a' && uc <= 'f')
? (uc - 'a' + 10) : (uc >= 'A' && uc <= 'F')
? (uc - 'A' + 10) : -1;
if (d == -1) {
[self addErrorWithCode:EUNICODE description:@"Missing hex digit in quad"];
return NO;
}
*x *= 16;
*x += d;
}
return YES;
}
- (BOOL)scanNumber:(NSNumber **)o
{
BOOL simple = YES;
const char *ns = c;
// The logic to test for validity of the number formatting is relicensed
// from JSON::XS with permission from its author Marc Lehmann.
// (Available at the CPAN: http://search.cpan.org/dist/JSON-XS/ .)
if ('-' == *c)
c++;
if ('0' == *c && c++) {
if (isdigit(*c)) {
[self addErrorWithCode:EPARSENUM description: @"Leading 0 disallowed in number"];
return NO;
}
} else if (!isdigit(*c) && c != ns) {
[self addErrorWithCode:EPARSENUM description: @"No digits after initial minus"];
return NO;
} else {
skipDigits(c);
}
// Fractional part
if ('.' == *c && c++) {
simple = NO;
if (!isdigit(*c)) {
[self addErrorWithCode:EPARSENUM description: @"No digits after decimal point"];
return NO;
}
skipDigits(c);
}
// Exponential part
if ('e' == *c || 'E' == *c) {
simple = NO;
c++;
if ('-' == *c || '+' == *c)
c++;
if (!isdigit(*c)) {
[self addErrorWithCode:EPARSENUM description: @"No digits after exponent"];
return NO;
}
skipDigits(c);
}
// If we are only reading integers, don't go through the expense of creating an NSDecimal.
// This ends up being a very large perf win.
if (simple) {
BOOL negate = NO;
long long val = 0;
const char *d = ns;
if (*d == '-') {
negate = YES;
d++;
}
while (isdigit(*d)) {
val *= 10;
if (val < 0)
goto longlong_overflow;
val += *d - '0';
if (val < 0)
goto longlong_overflow;
d++;
}
*o = [NSNumber numberWithLongLong:negate ? -val : val];
return YES;
} else {
// jumped to by simple branch, if an overflow occured
longlong_overflow:;
id str = [[NSString alloc] initWithBytesNoCopy:(char*)ns
length:c - ns
encoding:NSUTF8StringEncoding
freeWhenDone:NO];
[str autorelease];
if (str && (*o = [NSDecimalNumber decimalNumberWithString:str
locale:nil])) {
return YES;
}
[self addErrorWithCode:EPARSENUM description: @"Failed creating decimal instance"];
return NO;
}
}
- (BOOL)scanIsAtEnd
{
skipWhitespace(c);
return !*c;
}
@end
|